moonshotai / text-generation updated 3 months ago

Kimi-K2-Instruct

Name: Kimi-K2-Instruct
Author: moonshotai

- Messages with name field are now supported. We’ve also moved the chat template to a standalone file for easier viewing. - We further modified our chat template to improve its robustness. The default system prompt has also been updated. - We have updated our tokenizer implementation. Now special tokens like [EOS] can be encoded to their token ids. - We fixed a bug in the chat template that was breaking multi-turn to...

Params

1,026.5 B

Context

131,072

Downloads 30d

182 K

Likes

2,372

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

185 K168 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	1,029.2 GB	1,286.6 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	1,029.2 GB	3,596.1 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/kimi-k2-instruct
{
  "hf_id": "moonshotai/Kimi-K2-Instruct",
  "params_b": 1026.47,
  "context_length": 131072,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 182313,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 1286.6 }
  ],
  "updated_at": "2026-07-28T18:08:36Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: DeepseekV3ForCausalLM
Parameters: 1,026.5 B
Tensor type: F8_E4M3
Context length: 131,072
Vocabulary: 163,840
Layers / heads: 61 / 64
Licence: other
First seen on the Hub: 2025-07-11
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

DeepSeek-R1 9.9 M GLM-5.2-FP8 2.7 M GLM-5.2 2.2 M DeepSeek-V4-Pro 1.6 M DeepSeek-V3.2 1.2 M GLM-5-FP8 1.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB